Jung Hyuntae, Yethiraj Arun
Theoretical Chemistry Institute and Department of Chemistry, University of Wisconsin, Madison, Wisconsin 53706, USA.
J Chem Phys. 2020 Aug 14;153(6):064904. doi: 10.1063/5.0014194.
The phase behavior of complex fluids is a challenging problem for molecular simulations. Supervised machine learning (ML) methods have shown potential for identifying the phase boundaries of lattice models. In this work, we extend these ML methods to continuous-space systems. We propose a convolutional neural network model that utilizes grid-interpolated coordinates of molecules as input data of ML and optimizes the search for phase transitions with different filter sizes. We test the method for the phase diagram of two off-lattice models, namely, the Widom-Rowlinson model and a symmetric freely jointed polymer blend, for which results are available from standard molecular simulations techniques. The ML results show good agreement with results of previous simulation studies with the added advantage that there is no critical slowing down. We find that understanding intermediate structures near a phase transition and including them in the training set is important to obtain the phase boundary near the critical point. The method is quite general and easy to implement and could find wide application to study the phase behavior of complex fluids.
复杂流体的相行为对于分子模拟来说是一个具有挑战性的问题。监督式机器学习（ML）方法已显示出识别晶格模型相边界的潜力。在这项工作中，我们将这些ML方法扩展到连续空间系统。我们提出了一种卷积神经网络模型，该模型利用分子的网格插值坐标作为ML的输入数据，并通过不同的滤波器大小优化对相变的搜索。我们针对两个非晶格模型的相图测试了该方法，即维登 - 罗林森模型和对称自由连接的聚合物共混物，对于这两个模型，标准分子模拟技术可提供相关结果。ML结果与先前模拟研究的结果显示出良好的一致性，并且具有没有临界慢化的额外优势。我们发现理解相变附近的中间结构并将其纳入训练集对于获得临界点附近的相边界很重要。该方法非常通用且易于实现，并且可能在研究复杂流体的相行为方面找到广泛应用。
